Analytics Model

from sklearn.cluster import KMeans
from sklearn.preprocessing import StandardScaler
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
from sklearn.preprocessing import LabelEncoder
from sklearn.metrics import adjusted_rand_score
eda = pd.read_parquet("data/eda.parquet")

features = eda[['SALARY', 'MAX_YEARS_EXPERIENCE', 'MIN_YEARS_EXPERIENCE']].copy()

for col in ['MAX_YEARS_EXPERIENCE', 'MIN_YEARS_EXPERIENCE', 'SALARY']:
    features[col] = pd.to_numeric(features[col], errors='coerce')

features = features.dropna()

scaler = StandardScaler()
X = scaler.fit_transform(features)

kmeans = KMeans(n_clusters=4, random_state=688)
eda.loc[features.index, 'Cluster'] = kmeans.fit_predict(X)

true_labels = eda.loc[features.index, 'SOC_2021_4_NAME']
true_labels_encoded = LabelEncoder().fit_transform(true_labels)

ari = adjusted_rand_score(true_labels_encoded, eda.loc[features.index, 'Cluster'])

import plotly.express as px
import plotly.graph_objects as go
from IPython.display import HTML

df_plot = features.copy()
df_plot['Cluster'] = eda.loc[features.index, 'Cluster']

centroids = kmeans.cluster_centers_
centroids_x = centroids[:, 0] * X.std(axis=0)[0] + X.mean(axis=0)[0]
centroids_y = centroids[:, 1] * X.std(axis=0)[1] + X.mean(axis=0)[1]

fig = px.scatter(
    df_plot,
    x='SALARY',
    y='MAX_YEARS_EXPERIENCE',
    color='Cluster',
    title="KMeans Clustering by Salary and Max Years Experience",
    labels={
        'SALARY': 'Salary',
        'MAX_YEARS_EXPERIENCE': 'Max Years Experience',
        'Cluster': 'Cluster'
    },
    width=600,
    height=400,
)

fig.add_trace(
    go.Scatter(
        x=centroids_x,
        y=centroids_y,
        mode='markers',
        marker=dict(symbol='x', size=8, color='black', line=dict(width=2, color='white')),
        name='Centroids'
    )
)

fig.update_layout(
    legend=dict(
        title='Legend',
        x=1.3, 
        y=1,
        xanchor='left',
        yanchor='top',
    ),
    margin=dict(l=60, r=80, t=60, b=60)
)

fig.write_html(
    "figures/analytics_plot1.html",
    include_plotlyjs="cdn",
    full_html=True
)
fig.show()

Here we have 4 cluster groups. Group 0, which represent as green have lower salary, mostly under 150k, and max years experience in 2-5 years, it is likely Likely junior to mid-level employees with moderate pay. Group 1 with orange, has medium to high salary, wide range from $100k–$500k and with narrow range ~3 years, they are suggests specialized or high-paying roles with short experience — possibly fast-track promotions or high-demand fields. cluster 2 are low salary and experience from 0-4 years, they are clearly entry level employee. cluster 3 has medium salary, mostly under 200k with higher experiences, like 6-13 eyars. They probably are senior professionals with more experience but not the highest salaries.

import pandas as pd
from sklearn.linear_model import LinearRegression
from sklearn.model_selection import train_test_split
from sklearn.metrics import mean_squared_error, r2_score
import plotly.graph_objects as go

# Prepare features & target
features = eda[['MIN_YEARS_EXPERIENCE', 'MAX_YEARS_EXPERIENCE']].apply(pd.to_numeric, errors='coerce')
features = features.dropna()
X = features
y = eda.loc[X.index, 'SALARY']

# Train/test split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=688)

# Fit model & predict
model = LinearRegression()
model.fit(X_train, y_train)
y_pred = model.predict(X_test)

# Metrics (optional, but handy)
mse = mean_squared_error(y_test, y_pred)
r2 = r2_score(y_test, y_pred)
print(f"MSE: {mse:.2f}, R²: {r2:.3f}")

# Define min/max for the identity line
min_val = y_test.min()
max_val = y_test.max()

MSE: 797238619.53, R²: 0.095

import plotly.graph_objects as go

# Safety: make sure min_val and max_val are correctly defined
min_val = min(y_test.min(), y_pred.min())
max_val = max(y_test.max(), y_pred.max())

# Build figure
fig = go.Figure([
    go.Scatter(
        x=y_test,
        y=y_pred,
        mode='markers',
        marker=dict(
            color='skyblue',
            opacity=0.6,
            size=8
        ),
        name='Predicted vs Actual',
        hovertemplate='Actual: %{x:.2f}<br>Predicted: %{y:.2f}<extra></extra>'
    ),
    go.Scatter(
        x=[min_val, max_val],
        y=[min_val, max_val],
        mode='lines',
        line=dict(
            color='red',
            width=2,
            dash='dash'
        ),
        name='Ideal Fit',
        hoverinfo='skip'  # Don't show hover on the line
    )
])

# Update layout for better visual
fig.update_layout(
    title='Actual vs Predicted Salary (Multiple Regression)',
    xaxis_title='Actual Salary ($)',
    yaxis_title='Predicted Salary ($)',
    width=700,
    height=500,
    template='plotly_white',
    legend=dict(
        title='Legend',
        x=0.02,
        y=0.98,
        bordercolor='Gray',
        borderwidth=1
    ),
    margin=dict(l=60, r=40, t=60, b=60),
)

# Force equal scaling so that ideal line looks diagonal correctly
fig.update_yaxes(scaleanchor="x", scaleratio=1)

# Save HTML
fig.write_html(
    'figures/analytics_plot2.html',
    include_plotlyjs='cdn',
    full_html=False
)

fig.show()

This plot shows the Actual vs. Predicted Salary using a multiple linear regression model. The blue dots represent individual predictions, and the red dashed line is the ideal line where predicted = actual. Since most points lie very close to the red line, it means your model predicts salary very accurately, with minimal error and strong linear fit — likely reflected in a high R² score near 1.0.